Source-free cross-modal knowledge transfer is a crucial yet challenging task, which aims to transfer knowledge from one source modality (e.g., RGB) to the target modality (e.g., depth or infrared) with no access to the task-relevant (TR) source data due to memory and privacy concerns. A recent attempt leverages the paired task-irrelevant (TI) data and directly matches the features from them to eliminate the modality gap. However, it ignores a pivotal clue that the paired TI data could be utilized to effectively estimate the source data distribution and better facilitate knowledge transfer to the target modality. To this end, we propose a novel yet concise framework to unlock the potential of paired TI data for enhancing source-free cross-modal knowledge transfer. Our work is buttressed by two key technical components. Firstly, to better estimate the source data distribution, we introduce a Task-irrelevant data-Guided Modality Bridging (TGMB) module. It translates the target modality data (e.g., infrared) into the source-like RGB images based on paired TI data and the guidance of the available source model to alleviate two key gaps: 1) inter-modality gap between the paired TI data; 2) intra-modality gap between TI and TR target data. We then propose a Task-irrelevant data-Guided Knowledge Transfer (TGKT) module that transfers knowledge from the source model to the target model by leveraging the paired TI data. Notably, due to the unavailability of labels for the TR target data and its less reliable prediction from the source model, our TGKT model incorporates a self-supervised pseudo-labeling approach to enable the target model to learn from its predictions. Extensive experiments show that our method achieves state-of-the-art performance on three datasets (RGB-to-depth and RGB-to-infrared).
Unleashing Network Potentials for Semantic Scene Completion
School of Computer Science and Engineering, Nanjing University of Science & Technology（南京理工大学计算机科学与工程学院）；Singapore Management University（新加坡管理大学）；The Hong Kong University of Science & Technology（香港科技大学）
VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
School of Data Science, Fudan University（复旦大学数据科学学院）；ByteDance（字节跳动）；School of Computer Science, Fudan University（复旦大学计算机科学学院）；Research Institute of Intelligent and Complex Systems, Fudan University（复旦大学智能与复杂系统研究院）；Shanghai Innovation Institute（上海创新研究院）
Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；CAIR, HKISI, Chinese Academy of Sciences（中国科学院计算机辅助研究部）；School of Computer Science and Engineering, the Faculty of Innovation Engineering, M.U.S.T（慕斯科技大学计算机科学与工程学院）；Sangfor Technologies Inc.（Sangfor技术有限公司）；Beijing Jiaotong University（北京交通大学）；Alibaba Group（阿里巴巴集团）
Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation
Tencent Youtu Lab, Shanghai, China（腾讯优图实验室，上海，中国）；Xiamen University, Media Analytics（厦门大学，媒体分析）；Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen, China（计算实验室，人工智能系，信息学院，厦门，中国）
InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions
School of Computing and Artificial Intelligence（计算与人工智能学院）；Engineering Research Center of Intelligent Finance Ministry of Education（教育部长智能金融工程研究中心）；Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Electronic Science and Technology of China（电子科技大学）；Shanghai Academy of AI for Science（上海人工智能科学研究院）；Artificial Intelligence Innovation and Incubation Institute Fudan University（复旦大学人工智能创新与孵化院）；Artificial Intelligence and Digital Finance Key Laboratory of Sichuan Province（四川省人工智能与数字金融重点实验室）
Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis
School of Electronic Science and Engineering, Nanjing University（南京大学电子科学与工程学院）；School of Electronics Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）；Intel Lab China（英特尔中国实验室）
MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
Fujian Key Laboratory of Urban Intelligent Sensing and Computing（福建智能感知与计算重点实验室）；Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China（多媒体可信感知与高效计算重点实验室）；Beihang University（北航）；Nanyang Technological University（南洋理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；Zhongguancun Academy（中关村学院）
Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Technology and Standards Research Institute, China Academy of Information and Communications Technology（中国信息通信研究院技术与标准研究所）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Beijing Wenge Technology Co.,Ltd（北京文阁科技有限公司）
Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment
Beihang University（北京航空航天大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Tokyo Institute of Technology（东京工业大学）；University of Science and Technology of China（中国科学技术大学）；Zhongguancun Laboratory（中关村实验室）
